Comments (6)
在tensorflow中怎么实现呢?
from a-suozhang.github.io.
在tensorflow中怎么实现呢?
@chentianguang
您好,我个人不是很清楚tensorflow的接口,在pytorch中的batchnorm层是有一个running_mean/var的arg可以配置的,在新domain上可以手动修改,重新积累running_mean/var;此外,pytorch的默认behaviour是在model在train mode的时候依据输入数据,用momentum值滑动平均积累running mean/var,在eval模式时,则使用之前存储的running mean/var
from a-suozhang.github.io.
from a-suozhang.github.io.
from a-suozhang.github.io.
我使用tensorflow在训练集上得到训练好的模型,然后通过这行语句 for i in range(2000): model(x_demo,training=True),#此行语句是对x_demo进行预测,x_demo为测试集上的部分数据,测试集与训练集是不同源的数据。 ,使用测试集上的部分数据多次在训练好的模型上预测,最后发现模型在测试集上的效果有所提升,请问AdaBN表达的是这个意思吗? 发送自 Windows 10 版邮件<https://go.microsoft.com/fwlink/?LinkId=550986>应用 发件人: tianchenmailto:[email protected] 发送时间: 2020年9月10日 23:21 收件人: A-suozhang/A-suozhang.github.iomailto:[email protected] 抄送: chentianguangmailto:[email protected]; Commentmailto:[email protected] 主题: Re: [A-suozhang/A-suozhang.github.io] 论文阅读《Adaptive Batch Norm》 - 天辰的博客 | Tianchen's Blog (#39) 在tensorflow中怎么实现呢? 您好,我个人不是很清楚tensorflow的接口,在pytorch中的batchnorm层是有一个running_mean/var的arg可以配置的,在新domain上可以手动修改,重新积累running_mean/var;此外,pytorch的默认behaviour是在model在train mode的时候依据输入数据,用momentum值滑动平均积累running mean/var,在eval模式时,则使用之前存储的running mean/var ― You are receiving this because you commented. Reply to this email directly, view it on GitHub<#39 (comment)>, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AQ6FC63BZAJINBSIU6N6I2LSFDVIRANCNFSM4JCH7SVQ.
感觉大致是这个意思…就是在eval的时候在valid集合上独立积累BN的running_mean/var去做inference……(不过我自己测试的话感觉效果比较一般)
from a-suozhang.github.io.
你好,请问一下,这个adabn是怎么实现的啊?
from a-suozhang.github.io.
Related Issues (20)
- 论文阅读笔记《Billion-scale semi-supervised learning for image classification》 - 天辰的博客 | Tianchen's Blog
- 日知录 - 天辰的博客 | Tianchen's Blog
- 迁移学习 Transfer Learning - 天辰的博客 | Tianchen's Blog
- 卷积是如何加速的? - 天辰的博客 | Tianchen's Blog
- 日知录 - 天辰的博客 | Tianchen's Blog
- 大四上的课程 - 天辰的博客 | Tianchen's Blog
- Object Detection简述 - 天辰的博客 | Tianchen's Blog
- Understanding&Debugging PyTorch - 天辰的博客 | Tianchen's Blog
- 终于还是看起了HLS - 天辰的博客 | Tianchen's Blog
- Ubuntu 配置心得 - 天辰的博客 | Tianchen's Blog
- Linux常用命令笔记 - 天辰的博客 | Tianchen's Blog
- dpu配置的设备树配置与驱动产生 - 天辰的博客 | Tianchen's Blog
- 迁移学习 Transfer Learning - 天辰的博客 | Tianchen's Blog
- 论文阅读《Return of frustratingly easy domain adaptation》 - 天辰的博客 | Tianchen's Blog
- 论文阅读《Deep Visual Domain Adaptation A Survey》 - 天辰的博客 | Tianchen's Blog
- 大四上的课程 - 天辰的博客 | Tianchen's Blog
- Python写脚本的一些常用操作 - 天辰的博客 | Tianchen's Blog
- Ubuntu 配置心得 - 天辰的博客 | Tianchen's Blog
- Eva0开发笔记 - 天辰的博客 | Tianchen's Blog
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from a-suozhang.github.io.